blog
Ideas ▪ Evidence ▪ Practice
Local AI, RAG, and agents: lessons on data, evidence, permissions, and cost that connect model evaluation with daily business workflows.
Blog
Things I build, questions I follow, and lessons along the way.
Structured Evaluation
02 / AI evaluation Structured AI outputs: valid JSON is only the first quality check
Agentic Retrieval
03 / Applied AI Agentic RAG in production: better retrieval, measurable answers
Coaching Evaluation
04 / Agents & evaluation AI coaching agents: useful feedback starts with reliable evaluation
BI Agents
05 / Data & intelligence Business intelligence agents need a shared definition of the numbers
Local Inference
06 / AI strategy Local AI for business: when on-premises LLMs make sense
A Year of Large Transform(ers/ation): An NLP Engineer's Career Reflection
07 / Archive
A Cordial Invitation to Collaborate
08 / Archive
New year, New NLP: An Upgraded Stack for 2023 (Part 1)
09 / Archive
How I stopped worrying and learned to love Trustlessness
10 / Archive
PhD obtained and dissertation published.
11 / Archive
Public PhD Defense Gilles Jacobs
12 / Archive
Workshop on NLP for Economics
13 / Archive
New publications on extracting events and sentiment for financial news
14 / Archive
CLIN31: Join our session on COVID19 Stance and Opinion and poster on financial polar facts.
15 / Archive
Extracting Fine-Grained Economic Events from Business News.
16 / Archive
Publication: Automatic classification of participant roles in cyberbullying
17 / Archive
Publication: Current limitations in cyberbullying detection
18 / Archive
PyTorch GPU Stack in 5 minutes or less
19 / Archive
Wanted Annotator at LT3, UGent.
20 / Archive
A Cyborg Implant That Suits You: Exploring NFC Smartcard Tools
21 / Archive
Tame the Snake: Python Package Management with Pyenv, Pipenv & Pipx
22 / Archive
Announcing a New Economic Event Dataset @ ATILA18
23 / Archive
Presenting Economic Event Detection @ ACL18.
24 / Archive
Wanted Annotator at LT3, UGent.
25 / Archive
